Segmentation of Radiographs of Hands with Joint Damage Using Customized Active Appearance Models

摘要

This paper is part of a project that investigates the possibilities of automating the assessment of joint damagein hand radiographs. Our goal is to design a robust segmentationalgorithm for the hand skeleton. The algorithm isudbased on active appearance models (AAM) [1], which have been used for hand segmentation before [2]. The results will be used in the future for radiographic assessment of rheumatoid arthritis and the early detection of joint damage. New in this work with respect to [2] is the use of multiple object warps for each individual bone in a single AAM. This method prevents modelling and reconstruction defects caused when warping overlapping objects. This makes the algorithm more robust in cases where joint damage is present. The current implementation of the model includes the metacarpals, the phalanges, and the carpal region. For a first experimental evaluation a collection of 50 hand radiographs has been gathered. The image data set was split into a training set (40) and a test set (10) in order to evaluate the algorithm’s performance. First results show that in 8 images from the test set the bone contours are detected correctly within 1.3 mm (1 STD) at 15 pixels/cm resolution. In two images not all contours are detected correctly. Possibly this is caused by extreme deviations in these images that have not yet been incorporated in the model due to a limited training set. More training examples are needed to optimize the AAM and improve the quality and reliability of the results.